Personalised Explanations in Long-term Human-Robot Interactions

TL;DR

This paper introduces a framework for personalising explanations in long-term human-robot interactions, enhancing understanding by adapting explanation detail based on user knowledge, evaluated through LLM-based architectures in real-world scenarios.

Contribution

It proposes a novel framework for updating user knowledge models to personalise explanations, evaluated with three LLM-based architectures in practical HRI scenarios.

Findings

Two-stage architecture effectively personalises explanations based on user knowledge.

Personalisation reduces unnecessary detail, improving user understanding.

Framework adapts explanations dynamically over long-term interactions.

Abstract

In the field of Human-Robot Interaction (HRI), a fundamental challenge is to facilitate human understanding of robots. The emerging domain of eXplainable HRI (XHRI) investigates methods to generate explanations and evaluate their impact on human-robot interactions. Previous works have highlighted the need to personalise the level of detail of these explanations to enhance usability and comprehension. Our paper presents a framework designed to update and retrieve user knowledge-memory models, allowing for adapting the explanations' level of detail while referencing previously acquired concepts. Three architectures based on our proposed framework that use Large Language Models (LLMs) are evaluated in two distinct scenarios: a hospital patrolling robot and a kitchen assistant robot. Experimental results demonstrate that a two-stage architecture, which first generates an explanation and then personalises it, is the framework architecture that effectively reduces the level of detail only when there is related user knowledge.